FlatLands: Generative Floormap Completion From a Single Egocentric View
This work addresses the need for complete indoor maps for applications like navigation, but it is incremental as it builds on existing datasets and focuses on benchmarking.
The authors tackled the problem of generating a complete metric traversability map from a single egocentric view, which typically captures only a small portion of the floor, by introducing FlatLands, a dataset and benchmark with 270,575 observations from 17,656 real indoor scenes, and they compared various models including training-free approaches and generative methods.
A single egocentric image typically captures only a small portion of the floor, yet a complete metric traversability map of the surroundings would better serve applications such as indoor navigation. We introduce FlatLands, a dataset and benchmark for single-view bird's-eye view (BEV) floor completion. The dataset contains 270,575 observations from 17,656 real metric indoor scenes drawn from six existing datasets, with aligned observation, visibility, validity, and ground-truth BEV maps, and the benchmark includes both in- and out-of-distribution evaluation protocols. We compare training-free approaches, deterministic models, ensembles, and stochastic generative models. Finally, we instantiate the task as an end-to-end monocular RGB-to-floormaps pipeline. FlatLands provides a rigorous testbed for uncertainty-aware indoor mapping and generative completion for embodied navigation.